bcache: add CACHE_SET_IO_DISABLE to struct cache_set flags

When too many I/Os failed on cache device, bch_cache_set_error() is called
in the error handling code path to retire whole problematic cache set. If
new I/O requests continue to come and take refcount dc->count, the cache
set won't be retired immediately, this is a problem.

Further more, there are several kernel thread and self-armed kernel work
may still running after bch_cache_set_error() is called. It needs to wait
quite a while for them to stop, or they won't stop at all. They also
prevent the cache set from being retired.

The solution in this patch is, to add per cache set flag to disable I/O
request on this cache and all attached backing devices. Then new coming I/O
requests can be rejected in *_make_request() before taking refcount, kernel
threads and self-armed kernel worker can stop very fast when flags bit
CACHE_SET_IO_DISABLE is set.

Because bcache also do internal I/Os for writeback, garbage collection,
bucket allocation, journaling, this kind of I/O should be disabled after
bch_cache_set_error() is called. So closure_bio_submit() is modified to
check whether CACHE_SET_IO_DISABLE is set on cache_set->flags. If set,
closure_bio_submit() will set bio->bi_status to BLK_STS_IOERR and
return, generic_make_request() won't be called.

A sysfs interface is also added to set or clear CACHE_SET_IO_DISABLE bit
from cache_set->flags, to disable or enable cache set I/O for debugging. It
is helpful to trigger more corner case issues for failed cache device.

Changelog
v4, add wait_for_kthread_stop(), and call it before exits writeback and gc
    kernel threads.
v3, change CACHE_SET_IO_DISABLE from 4 to 3, since it is bit index.
    remove "bcache: " prefix when printing out kernel message.
v2, more changes by previous review,
- Use CACHE_SET_IO_DISABLE of cache_set->flags, suggested by Junhui.
- Check CACHE_SET_IO_DISABLE in bch_btree_gc() to stop a while-loop, this
  is reported and inspired from origal patch of Pavel Vazharov.
v1, initial version.

Signed-off-by: Coly Li <colyli@suse.de>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Michael Lyle <mlyle@lyle.org>
Cc: Junhui Tang <tang.junhui@zte.com.cn>
Cc: Michael Lyle <mlyle@lyle.org>
Cc: Pavel Vazharov <freakpv@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

1 files changed, 28 insertions, 9 deletions

diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c
index 8f98ef1038d3..70092ada68e6 100644
--- a/drivers/md/bcache/writeback.c
+++ b/drivers/md/bcache/writeback.c
@@ -114,6 +114,7 @@ static void update_writeback_rate(struct work_struct *work)
 	struct cached_dev *dc = container_of(to_delayed_work(work),
 					     struct cached_dev,
 					     writeback_rate_update);
+	struct cache_set *c = dc->disk.c;
 
 	/*
 	 * should check BCACHE_DEV_RATE_DW_RUNNING before calling
@@ -123,7 +124,12 @@ static void update_writeback_rate(struct work_struct *work)
 	/* paired with where BCACHE_DEV_RATE_DW_RUNNING is tested */
 	smp_mb();
 
-	if (!test_bit(BCACHE_DEV_WB_RUNNING, &dc->disk.flags)) {
+	/*
+	 * CACHE_SET_IO_DISABLE might be set via sysfs interface,
+	 * check it here too.
+	 */
+	if (!test_bit(BCACHE_DEV_WB_RUNNING, &dc->disk.flags) ||
+	    test_bit(CACHE_SET_IO_DISABLE, &c->flags)) {
 		clear_bit(BCACHE_DEV_RATE_DW_RUNNING, &dc->disk.flags);
 		/* paired with where BCACHE_DEV_RATE_DW_RUNNING is tested */
 		smp_mb();
@@ -138,7 +144,12 @@ static void update_writeback_rate(struct work_struct *work)
 
 	up_read(&dc->writeback_lock);
 
-	if (test_bit(BCACHE_DEV_WB_RUNNING, &dc->disk.flags)) {
+	/*
+	 * CACHE_SET_IO_DISABLE might be set via sysfs interface,
+	 * check it here too.
+	 */
+	if (test_bit(BCACHE_DEV_WB_RUNNING, &dc->disk.flags) &&
+	    !test_bit(CACHE_SET_IO_DISABLE, &c->flags)) {
 		schedule_delayed_work(&dc->writeback_rate_update,
 			      dc->writeback_rate_update_seconds * HZ);
 	}
@@ -278,7 +289,7 @@ static void write_dirty(struct closure *cl)
 		bio_set_dev(&io->bio, io->dc->bdev);
 		io->bio.bi_end_io	= dirty_endio;
 
-		closure_bio_submit(&io->bio, cl);
+		closure_bio_submit(io->dc->disk.c, &io->bio, cl);
 	}
 
 	atomic_set(&dc->writeback_sequence_next, next_sequence);
@@ -304,7 +315,7 @@ static void read_dirty_submit(struct closure *cl)
 {
 	struct dirty_io *io = container_of(cl, struct dirty_io, cl);
 
-	closure_bio_submit(&io->bio, cl);
+	closure_bio_submit(io->dc->disk.c, &io->bio, cl);
 
 	continue_at(cl, write_dirty, io->dc->writeback_write_wq);
 }
@@ -330,7 +341,9 @@ static void read_dirty(struct cached_dev *dc)
 
 	next = bch_keybuf_next(&dc->writeback_keys);
 
-	while (!kthread_should_stop() && next) {
+	while (!kthread_should_stop() &&
+	       !test_bit(CACHE_SET_IO_DISABLE, &dc->disk.c->flags) &&
+	       next) {
 		size = 0;
 		nk = 0;
 
@@ -427,7 +440,9 @@ static void read_dirty(struct cached_dev *dc)
 			}
 		}
 
-		while (!kthread_should_stop() && delay) {
+		while (!kthread_should_stop() &&
+		       !test_bit(CACHE_SET_IO_DISABLE, &dc->disk.c->flags) &&
+		       delay) {
 			schedule_timeout_interruptible(delay);
 			delay = writeback_delay(dc, 0);
 		}
@@ -583,11 +598,13 @@ static bool refill_dirty(struct cached_dev *dc)
 static int bch_writeback_thread(void *arg)
 {
 	struct cached_dev *dc = arg;
+	struct cache_set *c = dc->disk.c;
 	bool searched_full_index;
 
 	bch_ratelimit_reset(&dc->writeback_rate);
 
-	while (!kthread_should_stop()) {
+	while (!kthread_should_stop() &&
+	       !test_bit(CACHE_SET_IO_DISABLE, &c->flags)) {
 		down_write(&dc->writeback_lock);
 		set_current_state(TASK_INTERRUPTIBLE);
 		/*
@@ -601,7 +618,8 @@ static int bch_writeback_thread(void *arg)
 		    (!atomic_read(&dc->has_dirty) || !dc->writeback_running)) {
 			up_write(&dc->writeback_lock);
 
-			if (kthread_should_stop()) {
+			if (kthread_should_stop() ||
+			    test_bit(CACHE_SET_IO_DISABLE, &c->flags)) {
 				set_current_state(TASK_RUNNING);
 				break;
 			}
@@ -637,6 +655,7 @@ static int bch_writeback_thread(void *arg)
 
 			while (delay &&
 			       !kthread_should_stop() &&
+			       !test_bit(CACHE_SET_IO_DISABLE, &c->flags) &&
 			       !test_bit(BCACHE_DEV_DETACHING, &dc->disk.flags))
 				delay = schedule_timeout_interruptible(delay);
 
@@ -644,8 +663,8 @@ static int bch_writeback_thread(void *arg)
 		}
 	}
 
-	dc->writeback_thread = NULL;
 	cached_dev_put(dc);
+	wait_for_kthread_stop();
 
 	return 0;
 }